Continuing Lane Driving Prediction

Abstract

The technology relates to controlling a vehicle in an autonomous driving mode in accordance with behavior predictions for other road users in the vehicle's vicinity. In particular, the vehicle's onboard computing system may predict whether another road user will perform a “continuing” lane driving operation, such as going straight in a turn-only lane. Sensor data from detected/observed objects in the vehicle's nearby environment may be evaluated in view of one or more possible behaviors for different types of objects. In addition, roadway features, in particular whether lane segments are connected in a roadgraph, are also evaluated to determine probabilities of whether other road users may make an improper continuing lane driving operation. This is used to generate more accurate behavior predictions, which the vehicle can use to take alternative (e.g., corrective) driving actions.

1 . A method comprising:
 receiving, by one or more sensors of a perception system of a vehicle operating in an autonomous driving mode, sensor data associated with objects in an external environment of the vehicle including a road user within a lane;   determining, by one or more processors, indicia of a permitted driving behavior for road users traveling within the lane;   based on the sensor data, generating, by the one or more processors, a continuing lane driving behavior prediction for the road user indicating a likelihood that the road user follows the permitted driving behavior indicated by the determined indicia; and   controlling, by the one or more processors, the vehicle in the autonomous driving mode based on the continuing lane driving behavior prediction.   
     
     
         2 . The method of  claim 1 , wherein determining the indicia is based on map information related to a roadway including the lane. 
     
     
         3 . The method of  claim 1 , wherein determining the indicia is based on a stored roadgraph. 
     
     
         4 . The method of  claim 1 , wherein determining the indicia is based on the sensor data or other sensor data received from the perception system. 
     
     
         5 . The method of  claim 1 , wherein controlling the vehicle comprises accelerating more quickly than initially planned. 
     
     
         6 . The method of  claim 5 , wherein accelerating more quickly than initially planned comprises at least one of accelerating from a stop more quickly than initially planned or selecting a driving speed that is higher than an initially planned driving speed. 
     
     
         7 . The method of  claim 1 , wherein controlling the vehicle comprises waiting until the road user performs a movement before performing a planned maneuver. 
     
     
         8 . The method of  claim 1 , wherein generating the continuing lane driving behavior prediction comprises employing a machine learning model to evaluate at least the received sensor data and the indicia. 
     
     
         9 . The method of  claim 8 , wherein generating the continuing lane driving behavior prediction further comprises employing the machine learning model to evaluate at least one agent feature associated with the road user. 
     
     
         10 . The method of  claim 1 , wherein the permitted driving behavior includes performing a turn through an intersection. 
     
     
         11 . The method of  claim 1 , wherein the indicia comprises at least one of text or symbols presented on a surface of a roadway including the lane or text or symbols on at least one traffic sign. 
     
     
         12 . The method of  claim 1 , wherein: the indicia is based on a configuration of a roadway including the lane, and the configuration of the roadway is based on at least one of presence of lane dividers or designated turning lanes. 
     
     
         13 . A processing system comprising
 one or more processors configured to:
 receive, from one or more sensors of a perception system of a vehicle operating in an autonomous driving mode, sensor data associated with objects in an external environment of the vehicle including a road user within a lane; 
 determine indicia of a permitted driving behavior for road users traveling within the lane; 
 based on the sensor data, generate a continuing lane driving behavior prediction for the road user indicating a likelihood that the road user follows the permitted driving behavior indicated by the determined indicia; and 
 control the vehicle in the autonomous driving mode based on the continuing lane driving behavior prediction. 
   
     
     
         14 . The system of  claim 13 , wherein the one or more processors are configured to determine the indicia based on at least one of map information related to a roadway including the lane, a stored roadgraph, the sensor data, or other sensor data received from the perception system. 
     
     
         15 . The system of  claim 13 , wherein control of the vehicle comprises acceleration more quickly than initially planned, in which the acceleration more quickly than initially planned comprises at least one of acceleration from a stop more quickly than initially planned or selection of a driving speed that is higher than an initially planned driving speed. 
     
     
         16 . The system of  claim 13 , wherein control of the vehicle comprises waiting until the road user performs a movement before performance of a planned maneuver. 
     
     
         17 . The system of  claim 13 , wherein generation of the continuing lane driving behavior prediction employs a machine learning model to evaluate at least the received sensor data and the indicia or at least one agent feature associated with the road user. 
     
     
         18 . The system of  claim 13 , wherein the indicia comprises at least one of text or symbols presented on a surface of a roadway including the lane, text or symbols on at least one traffic sign, or a configuration of the roadway including the lane, and the configuration of the roadway is based on at least one of presence of lane dividers or designated turning lanes. 
     
     
         19 . A vehicle comprising:
 a driving system configured to control driving operations of the vehicle in an autonomous driving mode;   a perception system including one or more sensors configured to detect objects in an external environment of the vehicle; and   a control system including one or more processors, the control system operatively coupled to the driving system and the perception system, the control system being configured to:
 receive, from the perception system, sensor data associated with the detected objects, the detected objects at least including a road user within a lane; 
 determine indicia of a permitted driving behavior for road users traveling within the lane; 
 based on the sensor data, generate a continuing lane driving behavior prediction for the road user indicating a likelihood that the road user follows the permitted driving behavior indicated by the determined indicia; and 
 cause the driving system to control driving operations of the vehicle based on the continuing lane driving behavior prediction. 
   
     
     
         20 . The vehicle of  claim 19 , wherein the control system is configured to determine the indicia based on at least one of map information related to a roadway including the lane, a stored roadgraph, the sensor data, or other sensor data received from the perception system.